Table 6.
Optimal MAE and median percent error values for the out-of-distribution validation method.
|
Train MAEa | Validation MAE | Test MAE | Validation percent error | Test percent error |
Ridge regression | 0.296 | 0.240 | 0.247 | 2.26 | 1.22 |
Decision tree regression | 0.117 | 0.109 | 0.114 | 1.15 | 0.12 |
Random forest regression | 0.098 | 0.098 | 0.105 | 1.45 | 0.44 |
AdaBoostb regressionc | 0.207 | 0.081 | 0.089 | 1.40 | 0.39 |
Support vector regression | 0.268 | 0.167 | 0.176 | 1.66 | 0.60 |
aMAE: mean absolute error.
bAdaBoost: adaptive boosting.
cThe model with the lowest test MAE.